Network training method and apparatus for pose estimation, pose estimation method and apparatus, and electronic device, storage medium and computer program product

By training the pose network based on the existing feature extraction network, the problem of large consumption of head pose estimation algorithm in the prior art is solved, and more efficient pose estimation and lower computing resource occupation are achieved.

WO2025036450A9 Publication Date: 2025-04-03MOORE THREADS TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/112331
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-08-15
Filing Date
2024-08-15
Publication Date
2025-04-03

AI Technical Summary

Technical Problem

In the prior art, the algorithm for head pose estimation consumes a large amount of computing power and memory resources, which affects the real-time and efficiency of pose estimation.

Method used

A network training method for pose estimation is proposed. By obtaining the training data set, the sample image is input into the preset feature extraction network, the feature tensor of the target object is extracted, and the initial pose network is carried out multiple iterative training to obtain the target pose network. This method can be trained on the basis of the existing feature extraction network, reducing additional data preprocessing and training of the feature extraction network.

Benefits of technology

The target pose network trained through this method can be deployed on the existing feature extraction network during the inference stage, reducing the usage of computing resources, improving training efficiency, and reducing the consumption of processor computing resources and memory resources.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present disclosure relates to the technical field of computers, and relates to a network training method and apparatus for pose estimation, a pose estimation method and apparatus, and an electronic device, a storage medium and a computer program product. The network training method for pose estimation comprises: inputting a sample image, which is acquired from a training data set, into a preset feature extraction network; and performing training on an initial pose network according to a feature tensor, which is outputted by the feature extraction network, of a target object in the sample image, so as to obtain a target pose network. By means of the embodiments of the present disclosure, the training efficiency can be improved, thereby further reducing the consumption of computing power resources a processor and memory resources.
Need to check novelty before this filing date? Find Prior Art